LEME: Open-Sourced Large Language Models for Vision Research
Poster Number: P189
Presentation Time: 05:00 PM - 06:30 PM
Abstract Keywords: Natural Language Processing, Deep Learning, Machine Learning
Primary Track: Applications
Programmatic Theme: Clinical Informatics
Despite the potential of Large Language Models (LLMs) in healthcare, they lack domain specificity, often resulting in inaccurate, outdated, and hallucinated responses. Specifically, there is currently no publicly available LLM in Ophthalmology. This study aims to develop and validate EyeLLaMA – Ophthalmology domain-specific LLMs using over 150K instructions, covering six specific applications. The results demonstrate EyeLLaMA consistently outperformed other open-sourced LLMs by a large margin in all the applications.
Speaker(s):
Qingyu Chen, PhD
Yale University
Poster Number: P189
Presentation Time: 05:00 PM - 06:30 PM
Abstract Keywords: Natural Language Processing, Deep Learning, Machine Learning
Primary Track: Applications
Programmatic Theme: Clinical Informatics
Despite the potential of Large Language Models (LLMs) in healthcare, they lack domain specificity, often resulting in inaccurate, outdated, and hallucinated responses. Specifically, there is currently no publicly available LLM in Ophthalmology. This study aims to develop and validate EyeLLaMA – Ophthalmology domain-specific LLMs using over 150K instructions, covering six specific applications. The results demonstrate EyeLLaMA consistently outperformed other open-sourced LLMs by a large margin in all the applications.
Speaker(s):
Qingyu Chen, PhD
Yale University
LEME: Open-Sourced Large Language Models for Vision Research
Category
Poster Invite
Description
Date: Tuesday (11/12)
Time: 05:00 PM to 06:30 PM
Room: Grand Ballroom (Posters)
Time: 05:00 PM to 06:30 PM
Room: Grand Ballroom (Posters)